Data as of
Just Prompt for Windsurf: Setup & Config
Windsurf: Just Prompt lets an MCP assistant consult several language models and preserve their answers.
What you can do with Just Prompt in Windsurf
Keep model comparison, saved answers, and a panel's final decision within one MCP workflow.
- Reuse a prompt file and keep each model's output as a Markdown artifact.
- Discover provider-specific model choices before composing a multi-model request.
Before you start: Just Prompt in Windsurf
- Python and uv
- Local checkout with dependencies prepared using uv sync
- Credentials for chosen hosted providers, or an Ollama endpoint
This is the minimal README launch, not uv sync alone, which only prepares dependencies. The dot refers to the checkout directory; use the checkout's path if the client starts elsewhere. Provider values can be supplied by environment or .env. The optional --default-models argument chooses fallback models.
Just Prompt Windsurf configuration
Choose Windsurf configuration scope
For Just Prompt, open macOS/Linux: ~/.codeium/windsurf/mcp_config.json Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json. Merge into mcpServers; remote endpoints use serverUrl.
Add Just Prompt to Windsurf
Use the just-prompt entry below in mcpServers. Keep Just Prompt's documented stdio connection fields and your other Windsurf entries.
Check Just Prompt in Windsurf
Just Prompt: Refresh MCP in Windsurf settings and inspect Cascade’s tools.
Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json
Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json
{
"mcpServers": {
"just-prompt": {
"command": "uv",
"args": [
"--directory",
".",
"run",
"just-prompt"
],
"env": {
"OPENAI_API_KEY": "<credential if selecting OpenAI models>",
"ANTHROPIC_API_KEY": "<credential if selecting Anthropic models>",
"GEMINI_API_KEY": "<credential if selecting Gemini models>",
"GROQ_API_KEY": "<credential if selecting Groq models>",
"DEEPSEEK_API_KEY": "<credential if selecting DeepSeek models>",
"OLLAMA_HOST": "<address of the Ollama instance to consult>"
}
}
}
}Just Prompt tools available to Windsurf
Just Prompt's stored tool list documents 6 tools; compare it with Windsurf's connected tool list, because the stored list is not a live check.
- ceo_and_board
After refreshing Just Prompt in Windsurf settings, check Cascade's tool list for ceo_and_board.
- prompt_from_file_to_file
After refreshing Just Prompt in Windsurf settings, check Cascade's tool list for prompt_from_file_to_file.
- prompt_from_file
After refreshing Just Prompt in Windsurf settings, check Cascade's tool list for prompt_from_file.
Load prompt text from an absolute file path for the chosen models or default model set.
- prompt
After refreshing Just Prompt in Windsurf settings, check Cascade's tool list for prompt.
- list_models
After refreshing Just Prompt in Windsurf settings, check Cascade's tool list for list_models.
Discover model choices under one specified provider.
- list_providers
After refreshing Just Prompt in Windsurf settings, check Cascade's tool list for list_providers.
Inspect the provider options exposed by the server.
Troubleshooting Just Prompt in Windsurf
- Check uv on the machine running Windsurf's MCP integration for Just Prompt; refresh MCP and inspect Cascade's tools.
- Check ANTHROPIC_API_KEY, DEEPSEEK_API_KEY, GEMINI_API_KEY, GROQ_API_KEY, OLLAMA_HOST, OPENAI_API_KEY for Just Prompt; do not bypass a Windsurf permission error with a broad administrator token.
- Just Prompt uses stdio here: Windsurf must keep the configured process running; protocol output belongs on stdout and diagnostics on stderr.
- Known limitation: File-based operations require absolute prompt and output paths.
- Known limitation: Each hosted backend needs its own usable credential.
- Known limitation: Reasoning suffixes are tied to documented models and provider-specific limits.
- General Windsurf troubleshooting lives in the /clients/windsurf guide.
Just Prompt — details. Windsurf guide